Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Intel
/
phi-2-int4-inc
like
2
Follow
Intel
1,972
Text Generation
Transformers
Safetensors
NeelNanda/pile-10k
phi
text-generation-inference
Inference Endpoints
4-bit precision
intel/auto-round
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
phi-2-int4-inc
4 contributors
History:
30 commits
n1ck-guo
Update README.md
caca832
verified
26 days ago
.gitattributes
Safe
1.52 kB
initial commit
9 months ago
README.md
Safe
4.28 kB
Update README.md
26 days ago
added_tokens.json
Safe
1.08 kB
first commit
9 months ago
config.json
Safe
1.38 kB
upload autoround format
27 days ago
configuration_phi.py
Safe
2.03 kB
first commit
9 months ago
generation_config.json
Safe
119 Bytes
upload auto_gptq format
27 days ago
merges.txt
Safe
456 kB
first commit
9 months ago
model.safetensors
Safe
1.83 GB
LFS
upload auto_gptq format
27 days ago
modeling_phi.py
Safe
33.4 kB
first commit
9 months ago
quantization_config.json
Safe
573 Bytes
upload autoround format
27 days ago
special_tokens_map.json
Safe
441 Bytes
first commit
9 months ago
tokenizer.json
Safe
2.12 MB
upload auto_gptq format
27 days ago
tokenizer_config.json
Safe
7.37 kB
replace with sym quantization as there is a large accuracy drop due to kernel issue
6 months ago
vocab.json
Safe
798 kB
first commit
9 months ago